Achieving Efficient and Privacy-Preserving Neural Network Training and Prediction in Cloud Environments

• Published in: IEEE transactions on dependable and secure computing Vol. 20; no. 5; pp. 1 - 12
• Main Authors: Zhang, Chuan, Hu, Chenfei, Wu, Tong, Zhu, Liehuang, Liu, Ximeng
• Format: Journal Article
• Language: English
• Published: Washington IEEE 01.09.2023; IEEE Computer Society
• Subjects: Additively homomorphic cryptosystem; Cloud computing; cloud environments; Computational modeling; Computer privacy; Cryptography; Data collection; Data models; data perturbation; Data privacy; Face recognition; Image processing; neural network; Neural networks; Perturbation; Prediction models; Predictions; Predictive models; Privacy; privacy-preserving; Training

The neural network has been widely used to train predictive models for applications such as image processing, disease prediction, and face recognition. To produce more accurate models, powerful third parties (e.g., clouds) are usually employed to collect data from a large number of users, which howe...